Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    express

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    link
    -0.07
    \Modules
    -0.07
     hour
    -0.06
    อาช
    -0.06
     harms
    -0.06
     __________________
    -0.06
    _cookies
    -0.06
    '])){↵
    -0.06
     Saw
    -0.06
     dia
    -0.06
    POSITIVE LOGITS
    >/
    0.08
     Kaplan
    0.07
    房
    0.06
     HOH
    0.06
     modulo
    0.06
    =$
    0.06
     превыш
    0.06
    ()==
    0.06
    >M
    0.06
     Rory
    0.06
    Act Density 0.025%

    No Known Activations